docs: comprehensive docs audit — cover 13 features from last week's PRs (#5815)

Cover documentation gaps found by auditing all 50+ merged PRs from the past week:

tools-reference.md:
- Fix stale tool count (47→46, 11→10 browser tools) after browser_close removal
- Document notify_on_complete parameter in terminal tool description

telegram.md:
- Add Interactive Model Picker section (inline keyboard, provider/model drill-down)

discord.md:
- Add Interactive Model Picker section (Select dropdowns, 120s timeout)
- Add Native Slash Commands for Skills section (auto-registration at startup)

signal.md:
- Expand Attachments section with outgoing media delivery (send_image_file,
  send_voice, send_video, send_document via MEDIA: tags)

webhooks.md:
- Document {__raw__} special template token for full payload access
- Document Forum Topic Delivery via message_thread_id in deliver_extra

slack.md:
- Fix stale/misleading thread reply docs — thread replies no longer require
  @mention when bot has active session (3 locations updated)

security.md:
- Add cross-session isolation (layer 6) and input sanitization (layer 7)
  to security layers overview

feishu.md:
- Add WebSocket Tuning section (ws_reconnect_interval, ws_ping_interval)
- Add Per-Group Access Control section (group_rules with 5 policy types)

credential-pools.md:
- Add Delegation & Subagent Sharing section

delegation.md:
- Update key properties to mention credential pool inheritance

providers.md:
- Add Z.AI Endpoint Auto-Detection note
- Add xAI (Grok) Prompt Caching section

skills-catalog.md:
- Add p5js to creative skills category

website/docs/user-guide/security.md

@@ -10,13 +10,15 @@ Hermes Agent is designed with a defense-in-depth security model. This page cover
 
 ## Overview
 
-The security model has five layers:
+The security model has seven layers:
 
 1. **User authorization** — who can talk to the agent (allowlists, DM pairing)
 2. **Dangerous command approval** — human-in-the-loop for destructive operations
 3. **Container isolation** — Docker/Singularity/Modal sandboxing with hardened settings
 4. **MCP credential filtering** — environment variable isolation for MCP subprocesses
 5. **Context file scanning** — prompt injection detection in project files
+6. **Cross-session isolation** — sessions cannot access each other's data or state; cron job storage paths are hardened against path traversal attacks
+7. **Input sanitization** — working directory parameters in terminal tool backends are validated against an allowlist to prevent shell injection
 
 ## Dangerous Command Approval